用强化学习动态选文献，解决小样本下筛选效率低的问题
Autodiscover: A reinforcement learning recommendation system for the cold-start imbalance challenge in active learning, powered by graph-aware thompson sampling
- 将文献筛选建模为动态决策问题，基于图注意力网络捕捉文献关系
- 在26个数据集上比传统方法更高效，冷启动阶段仅需少量标签即可启动
- 支持实时人机协同，适合资源有限的系统性综述研究者使用
系统性文献综述（SLR）是循证研究的基础，但随着科研产出增长，人工筛选已成为瓶颈。筛选任务中相关研究占比低、专家标注成本高。传统主动学习（AL）系统依赖固定查询策略，无法随时间调整，且忽略文献间的关联结构。本文提出AutoDiscover，将主动学习重构为由自适应代理驱动的在线决策问题。文献被建模为异构图，包含文档、作者与元数据之间的关系；通过异构图注意力网络（HAN）学习节点表示，再由折扣汤普森采样（DTS）代理动态管理多种查询策略组合。在实时人机协同标注下，代理能平衡探索与利用，在非平稳的评审动态中适应策略效用变化。在26个数据集的SYNERGY基准上，AutoDiscover显著提升筛选效率。关键突破在于：仅需极少初始标签即可克服冷启动问题，而传统方法在此场景下失效。我们还开发了开源可视化分析工具TS-Insight，用于解释、验证和诊断代理决策。整体贡献推动了在专家标签稀缺、相关研究稀疏条件下的系统性文献综述加速。
原文摘要 · Abstract (English)
Systematic literature reviews (SLRs) are fundamental to evidence-based research, but manual screening is an increasing bottleneck as scientific output grows. Screening features low prevalence of relevant studies and scarce, costly expert decisions. Traditional active learning (AL) systems help, yet typically rely on fixed query strategies for selecting the next unlabeled documents. These static strategies do not adapt over time and ignore the relational structure of scientific literature networks. This thesis introduces AutoDiscover, a framework that reframes AL as an online decision-making problem driven by an adaptive agent. Literature is modeled as a heterogeneous graph capturing relationships among documents, authors, and metadata. A Heterogeneous Graph Attention Network (HAN) learns node representations, which a Discounted Thompson Sampling (DTS) agent uses to dynamically manage a portfolio of query strategies. With real-time human-in-the-loop labels, the agent balances exploration and exploitation under non-stationary review dynamics, where strategy utility changes over time. On the 26-dataset SYNERGY benchmark, AutoDiscover achieves higher screening efficiency than static AL baselines. Crucially, the agent mitigates cold start by bootstrapping discovery from minimal initial labels where static approaches fail. We also introduce TS-Insight, an open-source visual analytics dashboard to interpret, verify, and diagnose the agent's decisions. Together, these contributions accelerate SLR screening under scarce expert labels and low prevalence of relevant studies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。